Imitation learning enables robots to perform complex tasks by leveraging human-collected demonstrations. However, most existing approaches require labor-intensive data collection with additional teleoperation systems, which hinders scalability. Human videos represent a natural source of data that implicitly contain kno...
Guo-Ping Pan, Xin-Miao Yu, Wan-Nan Cao et al.· 0 citations
World action models improve robotic manipulation by conditioning actions on predicted futures, yet existing tactile variants largely inherit video-generation pipelines that reconstruct future tactile observations through iterative denoising. Such prediction can become unreliable under deployment drift: small changes in...
En-Yi Wang, Ming-Xin Wang, Quan Shi et al.· 0 citations
Physical interaction quality is central to deformable-object manipulation, yet most benchmarks evaluate task success alone. A policy may complete the task while allowing slip or causing excessive compression. A primary bottleneck is the absence of visuo-tactile datasets that pair policy-visible contact observations wit...
Bowen Jing, Ming-Xin Wang, Ruiyang Hao et al.· 0 citations
Imitation learning for robotics depends on human demonstrations, some of which people may later ask to remove. Retraining without them is the natural reference, but its cost grows with policy and dataset scale, motivating cheaper operators that edit a trained policy. Metrics inherited from machine unlearning, such as f...
Jia-Zhuo Li, Yu Zhang, Yi-Ming Fei et al.· 1 citation
DeviGrasp-Bench is introduced, a benchmark for mobile grasping under degraded vision that incorporates controlled visual degradations, seen and unseen objects, multiple difficulty levels, and complex terrains, and evaluates task success, execution efficiency, and action smoothness, and DeViGrasp-Net is proposed, a teac...
Liang Zhou, Jia-Ming Su, Yang Wei et al.· 0 citations
Latent world models that integrate a flow in a frozen self supervised latent space train stably and cheaply, yet silently lose the property manipulation depends on most: motion. The pretrained flow never moves the manipulated object; retraining it with latent-only losses only trades stillness for teleport-like motion....
Xi-Wen Chen, Rigaudiere Z. Li, Zhi-Ruo Zhou et al.· 0 citations
Semantic-Temporal WAM (ST-WAM) is proposed to improve action robustness by using DINOv3 as a shared semantic representation for future prediction and history retrieval while retaining fine-grained VAE dynamics, demonstrating that semantic-temporal modeling effectively complements pixel-generative dynamics for robust ma...
Mingxin Wang, Bin Hu, Bin Qian et al.· arXiv.org· 5 citations· ⚡1
Experiments show that STDR consistently improves sample efficiency and success rates over multiple baselines, and matches or surpasses handcrafted dense rewards on several challenging tasks, suggesting robustness to visual noise and better-calibrated reward assignment across settings.
Yang Yang, Bingjie Chen, Zihan Wang et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
